Back to skill

Security audit

Sora 478958

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Sora tutorial skill with broad activation wording but no code, persistence, credential access, or hidden behavior.

Installers should know this skill may appear for broad Sora questions; review whether that routing is acceptable, but there is no evidence it performs sensitive actions or changes the environment.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger string includes very broad terms such as "Sora" and "Sora2", which are likely to appear in ordinary conversation unrelated to this specific skill. That can cause unintended activation, leading the agent to inject this skill's guidance into contexts where it was not requested and reducing the reliability of skill routing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation condition "用户需要Sora相关帮助" is ambiguous and effectively matches a wide range of normal requests about Sora. This broad scope increases the chance of accidental invocation and context pollution, where the skill may override more appropriate behaviors or responses.

Content

No source excerpt is available for this finding.